© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 159477
    Prev
    Next
    INDEX
    Explanations

    clauses ending with common verbs

    np_acts-logits-general · gemini-2.5-flash-lite

    foundational skills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ish
    0.52
    а
    0.48
    𝒆
    0.48
     <=
    0.47
    _{
    0.46
     על
    0.46
    enni
    0.44
    _
    0.44
     בשנת
    0.43
    akin
    0.43
    POSITIVE LOGITS
     Literatura
    0.47
     vocab
    0.44
     quickSort
    0.43
     organizar
    0.43
     çöz
    0.42
     Literature
    0.42
     cosmos
    0.42
     nécessaire
    0.41
     Scene
    0.41
     happenings
    0.41
    Activations Density 0.000%

    No Known Activations